modelstatus.dev

Kimi K3

moonshotai/kimi-k3InputtextimagevideoOutputtext

Compare its 29 providersIncident RSSCompare with Kimi K2.7 Code, Kimi K2.6, Kimi K2.5

Showing only the wafer/us provider · show all 29

CompareKimi K3
  • Wafer100%
    Healthy24h 97.46%
    7d
    99.68%
    30d
    99.68%
    p50
    732ms
    p99
    20.1s
    Throughput
    46 tps
    Context
    1.0M
    $/Mtok
    $2.80 / $14.00
    wafer/us

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

Availability

Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.

Time to first token

Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window, averaged over the hour.

Throughput

Median tokens per second.

Daily availability

One row per endpoint · one dot per day · last 90 days.

Jul
Aug
Sep
Oct
morph/fp4
deepinfra/bf16
together
wafer
modal/mxfp4
phala
makora
relace/fp4
morph/fp8
digitalocean
morph/fast
decart/mxfp4
baseten/fp8
fireworks/us
chutes/mxfp4
inference-net
moonshotai/mxfp4
inference-net/fp4
parasail/fp4
fireworks/fast
fireworks
alibaba
morph
sail-research/fp4
inference-net/fast
amazon-bedrock/us-east-2
wafer/us
deepinfra/mxfp4
akashml/fp4
worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 29 endpoints · 48 days with data, 241 endpoint-days below 90%. Tables and charts above are filtered to wafer/us.

Price changes

  • Kimi K3Waferwafer$1.15 / $15.00cache read $0.375 → $0.4502026-10-05 01:55 UTC
  • Kimi K3Relacerelace/fp4$0.540 → $0.660 / $13.002026-10-05 01:55 UTC
  • Kimi K3Morphmorph/fp8$0.550 → $0.875 / $11.902026-10-05 01:46 UTC
  • Kimi K3Relacerelace/fp4$0.390 → $0.540 / $13.002026-10-05 01:40 UTC
  • Kimi K3Morphmorph/fp8$0.400 → $0.550 / $11.20 → $11.902026-10-05 01:31 UTC
  • Kimi K3Relacerelace/fp4$0.660 → $0.390 / $13.002026-10-05 01:20 UTC
  • Kimi K3Morphmorph/fp8$0.400 / $4.03 → $11.202026-10-05 01:20 UTC
  • Kimi K3Morphmorph/fp8$0.675 → $0.400 / $4.032026-10-05 01:16 UTC
  • Kimi K3Relacerelace/fp4$0.665 → $0.660 / $13.002026-10-05 01:05 UTC
  • Kimi K3InferenceNetinference-net/fp4$0.720 → $0.670 / $14.00cache read $0.700 → $0.6602026-10-05 01:01 UTC
  • Kimi K3Relacerelace/fp4$0.710 → $0.665 / $13.002026-10-05 00:45 UTC
  • Kimi K3Morphmorph/fp8$0.984 → $0.675 / $4.032026-10-05 00:35 UTC
  • Kimi K3InferenceNetinference-net/fast$3.75 → $3.50 / $20.002026-10-05 00:35 UTC
  • Kimi K3Morphmorph/fp8$1.91 → $0.984 / $9.19 → $4.032026-10-05 00:25 UTC
  • Kimi K3Relacerelace/fp4$0.662 → $0.710 / $13.002026-10-05 00:20 UTC
  • Kimi K3Relacerelace/fp4$0.657 → $0.662 / $13.002026-10-05 00:10 UTC
  • Kimi K3InferenceNetinference-net/fast$4.00 → $3.75 / $20.002026-10-05 00:01 UTC
  • Kimi K3Waferwafer$1.15 / $13.00 → $15.00cache read $0.300 → $0.3752026-10-04 23:51 UTC
  • Kimi K3InferenceNetinference-net/fast$3.75 → $4.00 / $20.002026-10-04 22:51 UTC
  • Kimi K3InferenceNetinference-net/fast$3.50 → $3.75 / $20.002026-10-04 22:31 UTC
  • Kimi K3Relacerelace/fp4$0.648 → $0.657 / $13.002026-10-04 22:10 UTC
  • Kimi K3Waferwafer$0.950 → $1.15 / $13.002026-10-04 22:05 UTC
  • Kimi K3Morphmorph/fp8$2.03 → $1.91 / $9.87 → $9.192026-10-04 21:40 UTC
  • Kimi K3Relacerelace/fp4$0.642 → $0.648 / $13.002026-10-04 21:31 UTC
  • Kimi K3InferenceNetinference-net/fp4$0.720 / $13.00 → $14.002026-10-04 21:16 UTC
  • Kimi K3Relacerelace/fp4$0.636 → $0.642 / $13.002026-10-04 20:56 UTC
  • Kimi K3InferenceNetinference-net/fast$3.75 → $3.50 / $20.002026-10-04 20:51 UTC
  • Kimi K3Relacerelace/fp4$0.630 → $0.636 / $13.002026-10-04 20:40 UTC
  • Kimi K3InferenceNetinference-net/fast$3.50 → $3.75 / $20.002026-10-04 20:31 UTC
  • Kimi K3Relacerelace/fp4$0.638 → $0.630 / $13.002026-10-04 20:16 UTC